© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6278
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of clearing or removing something from a situation

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

    "clear" and its variations

    np_acts-logits-general · gemini-2.0-flash

    clearing and removing

    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
    PreferredItem
    -0.52
     strconv
    -0.49
    glEnd
    -0.48
    StoryboardSegue
    -0.48
     awakeFromNib
    -0.47
     alignItems
    -0.47
     useAuth
    -0.46
    setVerticalGroup
    -0.46
     pym
    -0.46
    bootstrapcdn
    -0.45
    POSITIVE LOGITS
     clearing
    1.39
     cleared
    1.34
    Clearing
    1.27
     Clearing
    1.24
     clearance
    1.24
     clears
    1.23
    clearing
    1.19
     Clearance
    1.17
    cleared
    1.16
    clearance
    1.11
    Activations Density 0.282%

    No Known Activations