Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8443
    Prev
    Next
    INDEX
    Explanations

    elements related to skills development and improvement across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.55
    WriteBarrier
    -0.50
    astify
    -0.49
    localctx
    -0.47
    !*\
    -0.45
     oprot
    -0.45
    UnknownFieldSet
    -0.44
    دانشنامهٔ
    -0.43
     zac
    -0.42
    CopyWith
    -0.41
    POSITIVE LOGITS
     skills
    3.06
     skill
    2.91
    skills
    2.53
     Skills
    2.41
    skill
    2.39
    Skills
    2.27
     Skill
    2.23
    Skill
    2.22
     SKILLS
    2.11
    技能
    1.95
    Activations Density 0.544%

    No Known Activations