© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 2404
    Prev
    Next
    INDEX
    Explanations

    religious commitments and affirmations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    509
    +0.14
    0.4%
    1446
    +0.11
    0.3%
    1842
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.14
    0.06
    1380
    +0.11
    0.03
    1446
    +0.11
    0.03
    Negative Logits
    )_/¯
    -0.63
     izvē
    -0.59
    feitura
    -0.47
     يتيمه
    -0.46
    DoubleQuotes
    -0.46
    Garantie
    -0.46
    Giới
    -0.46
    ಠ
    -0.45
    Rusia
    -0.45
     newBuilder
    -0.45
    POSITIVE LOGITS
     stockholm
    1.06
     squa
    1.04
     affor
    1.02
     gtr
    1.01
     michelin
    1.01
     lola
    0.97
     wien
    0.96
     mcdonald
    0.96
     lidl
    0.96
     strick
    0.94
    Activations Density 0.230%

    No Known Activations