© 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. 90
    Prev
    Next
    INDEX
    Explanations

    words related to database and technical support

    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%
    394
    +0.06
    0.3%
    1288
    +0.04
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.10
    0.25
    1870
    +0.06
    0.01
    2011
    +0.04
    0.09
    Negative Logits
    <bos>
    -1.70
    public
    -0.89
    ’
    -0.88
    if
    -0.86
    /**
    
    -0.83
    /**
    -0.83
    .
    -0.83
    protected
    -0.83
     of
    -0.83
    //
    -0.82
    POSITIVE LOGITS
     increa
    2.29
     affor
    2.29
     Juf
    2.23
     maneu
    2.18
     aen
    2.15
     impra
    2.13
     emphat
    2.09
     stockholm
    2.06
     Augu
    2.06
     dises
    2.05
    Activations Density 6.293%

    No Known Activations