© 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. 18-GEMMASCOPE-RES-16K
    6. 4798
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantitative measurements and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical operations or formulas

    np_acts-logits-general · gemini-2.0-flash

    math operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    };*/
    -0.83
    "]);
    
    -0.68
    )"),
    -0.66
    )))));
    -0.64
     }}$}
    -0.63
    :]:
    -0.61
    })$}
    -0.61
    "])
    
    -0.61
    "]);
    -0.61
    ...");
    
    -0.60
    POSITIVE LOGITS
     plus
    1.65
     minus
    1.55
     multiplied
    1.46
     плюс
    1.39
     PLUS
    1.31
    plus
    1.27
     Plus
    1.23
     combined
    1.17
     divided
    1.14
    Plus
    1.12
    Activations Density 1.289%

    No Known Activations