© 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. 12941
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographical locations

    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
    667
    +0.12
    0.4%
    991
    +0.11
    0.4%
    474
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.12
    0.09
    981
    +0.11
    0.09
    1597
    +0.11
    0.04
    Negative Logits
     disreg
    -1.07
     intersper
    -0.98
     cushi
    -0.93
     reluct
    -0.89
     increa
    -0.86
     suscep
    -0.86
     disagre
    -0.83
     impra
    -0.82
     intermitt
    -0.80
     scrat
    -0.79
    POSITIVE LOGITS
     T
    0.63
    T
    0.61
    TD
    0.57
     TD
    0.56
    tau
    0.55
    TS
    0.54
    TB
    0.54
    TF
    0.54
     t
    0.53
    TP
    0.51
    Activations Density 0.697%

    No Known Activations