© 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. 15-GEMMASCOPE-RES-16K
    6. 1940
    Prev
    Next
    INDEX
    Explanations

    numerical dates, particularly in the context of historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -1.02
    tagHelperRunner
    -0.94
     onPostExecute
    -0.92
    Tikang
    -0.92
    awtextra
    -0.90
    verwijspagina
    -0.87
    ]));
    
    -0.85
    }));
    
    -0.82
     snippetHide
    -0.82
    ValueStyle
    -0.80
    POSITIVE LOGITS
    1
    0.66
    0
    0.57
     Sal
    0.53
    9
    0.51
    5
    0.51
    6
    0.51
    2
    0.51
     Lou
    0.49
    4
    0.47
     Ro
    0.47
    Activations Density 0.166%

    No Known Activations