© 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. 873
    Prev
    Next
    INDEX
    Explanations

    titles or descriptions related to military history or positions of authority

    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%
    1559
    +0.07
    0.2%
    1624
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    782
    +0.07
    0.02
    1313
    +0.07
    0.02
    1783
    +0.06
    0.02
    Negative Logits
    <bos>
    -1.52
     trillion
    -0.79
    mtrl
    -0.75
    ,
    -0.70
    static
    -0.70
    djangoproject
    -0.68
    public
    -0.68
    mergeFrom
    -0.68
    -0.67
    styleType
    -0.66
    POSITIVE LOGITS
     maneu
    2.13
     impra
    2.07
     affor
    2.03
     suscep
    1.99
     embodi
    1.98
     milf
    1.93
     increa
    1.91
     scrat
    1.91
     emphat
    1.91
     hairc
    1.91
    Activations Density 0.153%

    No Known Activations