© 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. 31-GEMMASCOPE-RES-16K
    6. 9019
    Prev
    Next
    INDEX
    Explanations

    keywords related to software entities and frameworks

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

    technical and domain-specific terminology from specialized fields like programming, engineering, and science.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enfans
    -0.46
    ที่ยว
    -0.41
    väg
    -0.40
     varandra
    -0.40
     Inscrivez
    -0.39
     avoient
    -0.39
     plegable
    -0.39
    makaian
    -0.38
     garansi
    -0.38
     enseignants
    -0.38
    POSITIVE LOGITS
     TK
    0.66
     FB
    0.63
    简称
    0.62
    #+#
    0.61
     CM
    0.60
     PB
    0.60
     abbreviated
    0.60
     MM
    0.59
     LW
    0.59
     FF
    0.59
    Activations Density 1.698%

    No Known Activations