© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 338
    Prev
    Next
    INDEX
    Explanations

    terms and conditions or legal language in documents

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.28
    1.1%
    453
    +0.14
    0.5%
    478
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.28
    0.08
    1832
    +0.14
    0.05
    1419
    +0.06
    0.05
    Negative Logits
    <bos>
    -1.99
     started
    -0.69
     got
    -0.64
     went
    -0.64
     came
    -0.64
     seemed
    -0.63
    ,
    -0.63
     wanted
    -0.62
     began
    -0.62
     helped
    -0.62
    POSITIVE LOGITS
     lele
    1.56
     vasi
    1.54
     stockholm
    1.52
     seksi
    1.52
     wien
    1.52
     cabrio
    1.50
     saar
    1.49
     maroc
    1.48
     socie
    1.47
     „,
    1.46
    Activations Density 0.570%

    No Known Activations