© 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. 3612
    Prev
    Next
    INDEX
    Explanations

    connecting words/phrases indicating causation or relationships between concepts

    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
    25
    +0.11
    0.4%
    1328
    +0.11
    0.4%
    517
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1328
    +0.11
    0.03
    893
    +0.11
    0.03
    1602
    +0.11
    0.03
    Negative Logits
    allerie
    -0.56
    .$.
    -0.55
     =",
    -0.52
     boxe
    -0.50
     :",
    -0.49
    hastly
    -0.49
    onBlur
    -0.49
    pertise
    -0.48
    ,**
    -0.47
     gmbh
    -0.47
    POSITIVE LOGITS
     accepté
    0.58
     payé
    0.56
     Meille
    0.53
     préparé
    0.52
     BioLib
    0.52
     constaté
    0.52
     FOR
    0.52
     them
    0.52
     identifiés
    0.51
     anyone
    0.51
    Activations Density 0.148%

    No Known Activations