© 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. 722
    Prev
    Next
    INDEX
    Explanations

    statistical data and terms related to mathematical and legal analysis

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

    preceding code or math terms

    np_acts-logits-general · gemini-2.0-flash

    present, meant, extended, needed

    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
     our
    -0.45
    HomeAsUp
    -0.42
     tqdm
    -0.40
     isNameExpr
    -0.40
    ----</
    -0.40
     yourselves
    -0.39
    +#+#
    -0.38
     yourself
    -0.37
    Tja
    -0.36
    Ours
    -0.36
    POSITIVE LOGITS
    MigrationBuilder
    0.69
     oneself
    0.51
     člověk
    0.50
     można
    0.46
    migrationBuilder
    0.46
     ujednoznacz
    0.45
     lze
    0.45
     należy
    0.42
     ihtiyaç
    0.42
    shadowRadius
    0.42
    Activations Density 0.695%

    No Known Activations