© 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. 2-GEMMASCOPE-RES-16K
    6. 8277
    Prev
    Next
    INDEX
    Explanations

    the letter 'f' and characters associated with it, likely indicating a focus on words or terms starting with or heavily featuring 'f' 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 @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     manuelle
    -0.38
    Totale
    -0.37
    awsze
    -0.37
    ⋱
    -0.36
     bedien
    -0.36
     zám
    -0.36
     avviene
    -0.36
    Демо
    -0.35
     étrangère
    -0.35
     Khusus
    -0.35
    POSITIVE LOGITS
    <bos>
    0.69
    تقاوى
    0.60
     ویکی‌پدی
    0.56
     ProtoMessage
    0.54
    writeFieldEnd
    0.54
     {?}
    0.53
     }{@
    0.53
    ChildScrollView
    0.52
    MigrationBuilder
    0.52
     CreateTagHelper
    0.49
    Activations Density 0.240%

    No Known Activations