© 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. 681
    Prev
    Next
    INDEX
    Explanations

    important findings and implications in discussions or studies related to various topics

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

    preceding implications, goals, problems

    np_acts-logits-general · gemini-2.0-flash

    introduces important findings, goals, or outcomes

    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
    IsMutable
    -0.56
    +#+#
    -0.49
    elf
    -0.48
    posedge
    -0.47
     برانيه
    -0.46
    Pyx
    -0.45
    ValueStyle
    -0.44
    bitField
    -0.44
    tart
    -0.44
    EndContext
    -0.42
    POSITIVE LOGITS
     reason
    0.60
    Personendaten
    0.55
     thing
    0.54
     Infórmanos
    0.50
    objectif
    0.50
     pregunta
    0.47
     najbolj
    0.47
     goal
    0.47
     objective
    0.47
     intenção
    0.46
    Activations Density 0.632%

    No Known Activations