© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 951
    Prev
    Next
    INDEX
    Explanations

    names of authors and titles of publications

    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
    +0.07
    0.2%
    283
    +0.05
    0.2%
    620
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.07
    0.13
    283
    +0.05
    0.04
    1363
    +0.05
    0.08
    Negative Logits
    <bos>
    -1.52
    ,
    -1.04
    .
    -0.96
    ⓧ
    -0.96
     can
    -0.92
    <eos>
    -0.92
     do
    -0.91
     and
    -0.91
    ↵↵
    -0.89
     on
    -0.89
    POSITIVE LOGITS
     fta
    2.53
     ftu
    2.52
     wherea
    2.38
     affor
    2.37
     mef
    2.37
     squa
    2.36
     aen
    2.35
     increa
    2.35
     volunte
    2.35
     dises
    2.33
    Activations Density 1.142%

    No Known Activations