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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3180
    Prev
    Next
    INDEX
    Explanations

    phrases related to being "off" or removed from a state or location

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

    The token "off"

    np_acts-logits-general · gemini-2.0-flash

    off

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    KURZBESCHREIBUNG
    -0.57
    matchCondition
    -0.57
    bootstrapcdn
    -0.57
    yarnpkg
    -0.51
    MigrationBuilder
    -0.50
    trino
    -0.49
    iostream
    -0.49
    textLabel
    -0.48
     Theaters
    -0.47
    shadowRadius
    -0.46
    POSITIVE LOGITS
     off
    2.19
     Off
    2.02
    Off
    1.91
    off
    1.88
     OFF
    1.84
    OFF
    1.55
     offs
    1.40
    offs
    1.33
    オフ
    1.23
     オフ
    1.20
    Activations Density 0.086%

    No Known Activations