© 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-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8872
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations related to higher-dimensional algebra

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )}_
    -0.46
    }}+\
    -0.40
    })+\
    -0.40
    ings
    -0.40
    yntaxException
    -0.40
    "]/
    -0.40
     Sta
    -0.39
     ret
    -0.39
     التأ
    -0.38
    })}\
    -0.38
    POSITIVE LOGITS
    ^{(
    1.19
    ^{(\
    1.02
    _{(
    0.88
    ^{[
    0.84
    ^{-
    0.79
    _{\
    0.78
    _{[
    0.77
    ^{*
    0.73
    ^{\
    0.72
    }^{(
    0.70
    Activations Density 0.629%

    No Known Activations