© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 743
    Prev
    Next
    INDEX
    Explanations

    information related to medical conditions and health challenges, as well as terms associated with laboratory procedures and techniques like mass spectrometry and liquid chromatography

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.10
    0.5%
    1265
    +0.05
    0.3%
    752
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.10
    0.13
    511
    +0.05
    0.10
    1871
    +0.05
    0.03
    Negative Logits
    <bos>
    -1.37
     immer
    -0.99
     rowspan
    -0.96
    protected
    -0.93
    </tbody>
    -0.92
    ൊ
    -0.90
    ⓧ
    -0.89
     continue
    -0.89
    public
    -0.89
     mit
    -0.89
    POSITIVE LOGITS
     maneu
    3.30
     impra
    3.23
     affor
    3.21
     reluct
    3.20
     increa
    3.10
     shenan
    3.08
     accla
    3.07
     disagre
    3.03
     depic
    2.93
     strick
    2.89
    Activations Density 1.302%

    No Known Activations