© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2647
    Prev
    Next
    INDEX
    Explanations

    guidelines and recommendations related to maintenance and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.66
     surla
    -0.65
    ChildScrollView
    -0.52
     &___
    -0.51
    migrationBuilder
    -0.50
    abstractmethod
    -0.49
    ArgsConstructor
    -0.49
     tartalomajánló
    -0.45
    awtextra
    -0.44
    IBOutlet
    -0.43
    POSITIVE LOGITS
    rungsseite
    0.50
     ErrIntOverflow
    0.43
     including
    0.43
    ябре
    0.42
    djangoproject
    0.42
     disambiguazione
    0.41
     GeoNames
    0.40
    including
    0.39
     ब्रेकडाउन
    0.38
    Datuak
    0.38
    Activations Density 0.341%

    No Known Activations