© 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. 38-GEMMASCOPE-RES-16K
    11. 7956
    Prev
    Next
    INDEX
    Explanations

    phrases related to damages and repairs, especially in the context of physical or financial harm

    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
    IntoConstraints
    -0.40
    PreInfinity
    -0.31
    躇
    -0.31
    etCode
    -0.31
    HomeAsUpEnabled
    -0.30
     desenli
    -0.30
    resizingMask
    -0.30
    TagNumber
    -0.29
     CreateTagHelper
    -0.29
     الرخصة
    -0.29
    POSITIVE LOGITS
     damage
    3.31
     Damage
    2.89
    damage
    2.84
    Damage
    2.78
     DAMAGE
    2.58
     damages
    2.48
    DAMAGE
    2.27
     damaged
    2.19
     daño
    2.17
     Damages
    2.11
    Activations Density 0.878%

    No Known Activations