© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1444
    Prev
    Next
    INDEX
    Explanations

    instructions or steps related to processes and evaluations

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

    Steps in a process or method

    np_acts-logits-general · gemini-2.0-flash

    structured methods and processes

    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
    MigrationBuilder
    -0.60
    featureID
    -0.56
    TemporalType
    -0.54
    medriver
    -0.54
    borderSide
    -0.53
    SharedDtor
    -0.53
    webElement
    -0.51
     AssemblyVersion
    -0.50
    enderror
    -0.49
    InitStruct
    -0.48
    POSITIVE LOGITS
     process
    0.74
     tools
    0.67
     guided
    0.60
     structured
    0.58
     tool
    0.58
     Process
    0.57
     methodology
    0.57
     analysis
    0.57
     method
    0.56
     proses
    0.55
    Activations Density 0.399%

    No Known Activations