© 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. 237
    Prev
    Next
    INDEX
    Explanations

    mentions of depicting or representing

    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
    1334
    +0.08
    0.3%
    1101
    +0.08
    0.3%
    200
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    647
    +0.08
    0.02
    1141
    +0.08
    0.02
    1101
    +0.08
    0.02
    Negative Logits
    <bos>
    -0.85
    ുറ
    -0.67
    public
    -0.65
    multicolumn
    -0.62
    interface
    -0.58
    else
    -0.58
    unsigned
    -0.57
    int
    -0.57
    if
    -0.57
    struct
    -0.57
    POSITIVE LOGITS
     portray
    1.95
     depic
    1.95
     portrayal
    1.89
     depiction
    1.81
     portraying
    1.80
     depict
    1.75
     portrayed
    1.75
     portrays
    1.68
     depictions
    1.66
     depicting
    1.64
    Activations Density 0.092%

    No Known Activations