Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 55
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific brand or company name

    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
    1565
    +0.11
    0.3%
    544
    +0.11
    0.3%
    369
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.11
    0.04
    184
    +0.11
    0.02
    690
    +0.09
    0.04
    Negative Logits
     Herrick
    -0.74
     McLaugh
    -0.68
    <bos>
    -0.67
     Unger
    -0.66
     McFar
    -0.64
     Kearns
    -0.64
     McInt
    -0.64
     Kruse
    -0.57
     Hickey
    -0.57
     inform
    -0.57
    POSITIVE LOGITS
     Ottobre
    1.59
     Baldwin
    1.58
     broder
    1.54
     Settembre
    1.49
     cannes
    1.49
     marseille
    1.48
     Traité
    1.42
     Luglio
    1.41
     tyn
    1.41
     chèvre
    1.39
    Activations Density 0.299%

    No Known Activations