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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 1060
    Prev
    Next
    INDEX
    Explanations

    Java annotations for entity definition in object-relational mapping (ORM)

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

    Java annotations (e.g., @Entity, @Id, @Configuration)

    np_acts-logits-general · gemini-2.0-flash

    code annotations and biological/political terms

    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
     kaynağından
    -0.73
     تضيفلها
    -0.65
    Portály
    -0.61
     chi̍t
    -0.61
     }}$}
    -0.60
    _));
    -0.60
    xFFFFFF
    -0.60
    τικών
    -0.57
    )"),
    -0.57
    \"");
    -0.57
    POSITIVE LOGITS
     at
    1.61
    @
    1.23
    At
    1.11
     At
    1.06
     @
    0.98
    at
    0.96
     tại
    0.82
     AT
    0.74
    ...@
    0.64
     	e
    0.64
    Activations Density 0.015%

    No Known Activations