© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 9560
    Prev
    Next
    INDEX
    Explanations

    markers indicating the beginning of new sections or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }');
    -0.70
    WriteBarrier
    -0.70
    LookAnd
    -0.69
    __":
    -0.69
    );?>
    -0.68
    __':
    
    -0.65
    DoubleQuotes
    -0.64
    ScopeManager
    -0.64
    >';
    
    -0.64
    Datuak
    -0.64
    POSITIVE LOGITS
    izontal
    0.62
     ſmall
    0.60
     bordir
    0.60
     Lynd
    0.58
    adox
    0.58
     saveiro
    0.57
    adeloupe
    0.56
     purpoſe
    0.56
     Chriſt
    0.56
     fucking
    0.56
    Activations Density 0.122%

    No Known Activations