Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14041
    Prev
    Next
    INDEX
    Explanations

    specific references to locations and institutions, particularly in a medical or educational context

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

    Follows short, often foreign, words

    np_acts-logits-general · gemini-2.0-flash

    places and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nonatomic
    -0.50
    httphttps
    -0.49
    ]")]
    -0.47
     VizieR
    -0.47
    <?
    -0.47
    ChildScrollView
    -0.46
     zoll
    -0.46
    )_/¯
    -0.45
    észetes
    -0.43
     թվական
    -0.43
    POSITIVE LOGITS
    TagMode
    0.52
    RenderAtEndOf
    0.48
    SupportActionBar
    0.41
    Dichloroethane
    0.38
    CppMethod
    0.37
     opérés
    0.36
    TemporalType
    0.36
    Parcelize
    0.36
     unt
    0.35
    EndInit
    0.35
    Activations Density 0.791%

    No Known Activations