© 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. 14217
    Prev
    Next
    INDEX
    Explanations

    time and date-related patterns

    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
    2019
    +0.19
    0.6%
    1343
    +0.13
    0.4%
    871
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1274
    +0.19
    0.04
    1678
    +0.13
    0.04
    1990
    +0.11
    0.04
    Negative Logits
     Cruces
    -0.56
     autorytatywna
    -0.55
    quehanna
    -0.53
     emberek
    -0.52
     pelic
    -0.49
    报错
    -0.49
    AsUp
    -0.49
     folosit
    -0.48
    كتوبر
    -0.48
    SharedCtor
    -0.47
    POSITIVE LOGITS
     allarg
    1.01
     circon
    0.88
     credere
    0.86
     apparti
    0.86
     Kategor
    0.85
     saper
    0.83
     suscit
    0.82
     inol
    0.81
     sappi
    0.81
     espri
    0.80
    Activations Density 0.113%

    No Known Activations