© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12454
    Prev
    Next
    INDEX
    Explanations

    commands related to task management

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

    Commands/arguments after command-line tool name

    np_acts-logits-general · gemini-2.0-flash

    details and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Taktlose
    -0.54
    ########.
    -0.50
    fetchall
    -0.50
    WhereInput
    -0.46
    yntaxException
    -0.45
    protoimpl
    -0.44
     oprot
    -0.43
     enum
    -0.42
    addAll
    -0.42
    :+:
    -0.41
    POSITIVE LOGITS
     detail
    1.12
    detail
    1.05
     details
    1.04
     Detail
    1.04
    Detail
    0.99
     Details
    0.98
     detailed
    0.97
     Detailed
    0.96
    details
    0.93
    Details
    0.92
    Activations Density 0.211%

    No Known Activations