© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7126
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a need for analysis or understanding of mechanisms, functions, and relationships

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

    Following "to" and an action verb

    np_acts-logits-general · gemini-2.0-flash

    phrases starting with "to" for purpose

    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
    principalColumn
    -0.95
    parsedMessage
    -0.65
    PerformLayout
    -0.65
    StructEnd
    -0.64
    GraphicsUnit
    -0.64
     nakalista
    -0.64
     MainAxisSize
    -0.61
    ValueStyle
    -0.60
    tonode
    -0.59
    awtextra
    -0.59
    POSITIVE LOGITS
    Чтобы
    0.38
     Чтобы
    0.36
    Referències
    0.32
     needs
    0.29
     To
    0.29
     For
    0.28
     opaque
    0.28
    DataPropertyName
    0.28
    するため
    0.28
    To
    0.27
    Activations Density 0.773%

    No Known Activations