© 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. 7582
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person (possibly a sports figure) in various contexts

    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
    381
    +0.21
    0.8%
    1510
    +0.17
    0.6%
    1896
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.21
    0.09
    1637
    +0.17
    0.08
    521
    +0.13
    0.08
    Negative Logits
     nuoc
    -1.30
     quoc
    -1.26
     venuto
    -1.22
     thuy
    -1.20
     cioc
    -1.19
     susun
    -1.17
     persil
    -1.15
     ananas
    -1.13
     vinci
    -1.12
     chèvre
    -1.10
    POSITIVE LOGITS
    He
    1.07
     He
    1.05
     himself
    0.92
     he
    0.90
     Himself
    0.88
    he
    0.83
    himself
    0.82
    His
    0.81
     His
    0.74
    Он
    0.70
    Activations Density 0.259%

    No Known Activations