© 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. 13748
    Prev
    Next
    INDEX
    Explanations

    descriptions related to video game controls and virtual reality experiences

    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
    906
    +0.12
    0.3%
    1842
    +0.11
    0.3%
    1819
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1876
    +0.12
    0.03
    2044
    +0.11
    0.06
    946
    +0.09
    0.04
    Negative Logits
     reluct
    -1.73
     increa
    -1.71
     volunte
    -1.68
     encomp
    -1.64
     affor
    -1.64
     disagre
    -1.63
     accla
    -1.61
     embra
    -1.60
     suscep
    -1.57
     inev
    -1.56
    POSITIVE LOGITS
    <bos>
    0.79
    AddTagHelper
    0.70
    hyrchwyd
    0.68
     while
    0.65
    RTDA
    0.63
     simultaneously
    0.63
     monitor
    0.63
     watching
    0.63
    wijl
    0.61
    Personendaten
    0.61
    Activations Density 0.458%

    No Known Activations