© 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. 938
    Prev
    Next
    INDEX
    Explanations

    mentions of family-related terms

    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
    2034
    +0.10
    0.3%
    1926
    +0.10
    0.3%
    544
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1425
    +0.10
    0.03
    1926
    +0.10
    0.03
    544
    +0.10
    0.03
    Negative Logits
     répon
    -0.74
     exé
    -0.74
     appartiennent
    -0.71
     apparti
    -0.71
     alberto
    -0.70
     roberto
    -0.68
    Rgds
    -0.68
     quelquefois
    -0.67
     doté
    -0.67
     quoique
    -0.66
    POSITIVE LOGITS
     families
    1.10
     Families
    1.04
    families
    1.02
    Families
    0.96
     FAMIL
    0.74
     familias
    0.71
    DockStyle
    0.70
     PyTuple
    0.69
     Baillargeon
    0.68
     households
    0.66
    Activations Density 0.118%

    No Known Activations