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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 89338
    Prev
    Next
    INDEX
    Explanations

    references to specific regions or locations, and data structures formatted with specific parameters like dates

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

    spatial and state identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ])))
    -0.63
    })).
    -0.60
    "}},
    -0.58
     Wikimedijinoj
    -0.58
    ())));
    -0.58
    "]))
    -0.57
    "}>
    -0.57
     مرئيه
    -0.56
    rungsseite
    -0.55
    )))),
    -0.55
    POSITIVE LOGITS
    BeginInit
    0.57
     كومونز
    0.48
    omitempty
    0.45
    BagLayout
    0.43
    Personendaten
    0.39
     mList
    0.39
    PINES
    0.38
     GenerationType
    0.38
    WritableDatabase
    0.37
     للاسماء
    0.37
    Activations Density 0.346%

    No Known Activations