© 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. 24-GEMMASCOPE-RES-16K
    6. 707
    Prev
    Next
    INDEX
    Explanations

    technical terminology and mathematical expressions

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

    Mathematical or code-related symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical punctuation and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.58
     betweenstory
    -0.54
    Viited
    -0.51
    astify
    -0.51
    jspb
    -0.50
     allAfrica
    -0.48
     كورة
    -0.47
    MigrationBuilder
    -0.46
     gynhyrchwyd
    -0.45
    يكب
    -0.44
    POSITIVE LOGITS
     kaynağından
    0.39
     लेकिन
    0.39
     ancak
    0.38
     Ancak
    0.38
     зато
    0.37
     zato
    0.37
    但是
    0.36
     ContentValues
    0.36
     bật
    0.35
    但是在
    0.35
    Activations Density 0.704%

    No Known Activations