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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 376
    Prev
    Next
    INDEX
    Explanations

    information related to ecology and environmental topics

    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
    1034
    +0.08
    0.3%
    172
    +0.08
    0.3%
    196
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    262
    +0.08
    0.03
    613
    +0.08
    0.02
    1882
    +0.07
    0.02
    Negative Logits
    font
    -0.73
    <bos>
    -0.69
    തി
    -0.69
    write
    -0.68
    下
    -0.68
    മ
    -0.67
    }{||
    -0.67
    board
    -0.67
    public
    -0.66
    branch
    -0.66
    POSITIVE LOGITS
     stockholm
    2.24
     increa
    2.12
     affor
    2.07
     scrat
    2.00
     maneu
    1.99
     effe
    1.98
     guarante
    1.97
     secon
    1.96
     eiffel
    1.95
     wien
    1.95
    Activations Density 0.148%

    No Known Activations