© 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. 1062
    Prev
    Next
    INDEX
    Explanations

    mentions of specific terms in a book or product manual

    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
    0.4%
    1385
    +0.06
    0.3%
    394
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.10
    0.19
    16
    +0.06
    0.12
    1253
    +0.06
    0.10
    Negative Logits
    <bos>
    -2.13
    ,
    -0.84
    RuleContext
    -0.84
    RepeatedField
    -0.82
    public
    -0.82
    //
    -0.79
     &___
    -0.77
     of
    -0.77
    ’
    -0.77
    ുറ
    -0.77
    POSITIVE LOGITS
     affor
    2.15
     increa
    2.11
     maneu
    2.08
     stockholm
    1.98
     disagre
    1.97
     véhic
    1.97
     Juf
    1.97
     reluct
    1.96
     emphat
    1.95
     inev
    1.95
    Activations Density 4.035%

    No Known Activations