© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1662
    Prev
    Next
    INDEX
    Explanations

    structured introductions and categorizations of different concepts or entities

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

    Preceding tokens of "and" or grammatical conjunctions

    np_acts-logits-general · gemini-2.0-flash

    or and

    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
    }}$.
    -0.88
    ].
    -0.84
    \}.
    -0.82
    \}$.
    -0.80
    }$.
    -0.79
    }'.
    -0.77
    '].
    -0.76
    })$.
    -0.76
    "].
    -0.76
    )}$.
    -0.76
    POSITIVE LOGITS
     كومونز
    1.03
    TypedDataSet
    0.85
    OGND
    0.81
     تانيه
    0.80
    IntoConstraints
    0.78
     ujednoznacz
    0.77
     المعيارى
    0.74
    таратура
    0.73
     متعلقه
    0.73
     برانيه
    0.72
    Activations Density 1.016%

    No Known Activations