© 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. 0-RES-JB
    11. 529
    Prev
    Next
    INDEX
    Explanations

    information related to events and news articles, especially with dates and locations included

    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
    1271
    +0.11
    0.3%
    1491
    +0.11
    0.3%
    1296
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.11
    0.02
    1343
    +0.11
    0.02
    1907
    +0.09
    0.02
    Negative Logits
    ,
    -0.80
    in
    -0.77
     про
    -0.77
     snow
    -0.77
     có
    -0.76
     turn
    -0.75
     or
    -0.74
     win
    -0.74
     me
    -0.73
    เช
    -0.73
    POSITIVE LOGITS
     EDT
    2.59
     stockholm
    2.55
     fta
    2.37
     fte
    2.36
     ftu
    2.35
     increa
    2.29
     wien
    2.29
     ibiza
    2.29
     desir
    2.26
     madonna
    2.25
    Activations Density 0.181%

    No Known Activations