© 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. 7-GEMMASCOPE-RES-16K
    6. 15135
    Prev
    Next
    INDEX
    Explanations

    terms related to minor issues or discrepancies in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faſt
    -0.59
    ſelves
    -0.56
    httphttps
    -0.53
     Reſ
    -0.53
    ⟬
    -0.52
    MigrationBuilder
    -0.51
    Grath
    -0.50
    ſelf
    -0.49
     XCTest
    -0.48
     Majefty
    -0.48
    POSITIVE LOGITS
     minor
    2.48
    Minor
    2.27
     Minor
    2.22
    minor
    2.20
     MINOR
    2.03
    MINOR
    1.83
     minors
    1.23
     minore
    1.12
     insignificant
    1.09
     minori
    1.09
    Activations Density 0.287%

    No Known Activations