Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 8969
    Prev
    Next
    INDEX
    Explanations

    labels and parameters associated with figures and diagrams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.86
    LookAnd
    -0.81
    новниш
    -0.67
    })));
    -0.66
    :"-"`
    -0.65
    ьаж
    -0.62
    ///</
    -0.62
    ">—
    -0.61
    vician
    -0.61
    '],'
    -0.61
    POSITIVE LOGITS
     BoxFit
    0.65
    AutoScaleMode
    0.58
    =\
    0.57
     width
    0.53
     wic
    0.52
     Schmer
    0.52
     Width
    0.49
     réglable
    0.49
     getWidth
    0.48
     cref
    0.48
    Activations Density 0.037%

    No Known Activations