© 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. 7731
    Prev
    Next
    INDEX
    Explanations

    phrases related to virtual reality technology and gaming

    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
    1177
    +0.23
    0.8%
    1577
    +0.13
    0.5%
    1507
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.23
    0.11
    1177
    +0.13
    0.07
    227
    +0.10
    0.10
    Negative Logits
     far
    -0.96
     for
    -0.90
    ↵↵
    -0.89
     but
    -0.89
     to
    -0.89
     or
    -0.88
     from
    -0.88
     like
    -0.87
     on
    -0.86
     at
    -0.86
    POSITIVE LOGITS
     fta
    2.77
     ftu
    2.75
     effe
    2.73
     wien
    2.70
     stockholm
    2.69
     mef
    2.68
     fte
    2.64
     fto
    2.63
     ?...
    2.61
     emphat
    2.61
    Activations Density 0.958%

    No Known Activations