© 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. 31-GEMMASCOPE-RES-16K
    11. 2653
    Prev
    Next
    INDEX
    Explanations

    terms related to validation and invalidation

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

    the word "valid" and its morphological variants like "validating" and "invalidity".

    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
     BoxFit
    -0.40
     חיצוניים
    -0.38
     BytesLike
    -0.37
    Referințe
    -0.34
    ee
    -0.33
     typelib
    -0.31
    mę
    -0.31
    ről
    -0.31
    ThemeOverlay
    -0.30
    es
    -0.29
    POSITIVE LOGITS
    ating
    0.81
    ated
    0.80
    ATED
    0.66
    ATING
    0.65
    atable
    0.58
    ates
    0.56
    ators
    0.54
    cipline
    0.54
    acies
    0.54
    DataAnnotations
    0.52
    Activations Density 0.171%

    No Known Activations