© 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. 2807
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or notable characters

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

    abbreviations and acronyms, particularly those consisting of capital letters.

    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
    号
    -0.45
     propOrder
    -0.43
    ReusableCell
    -0.40
    ExtendWith
    -0.39
     favor
    -0.39
    RequiresApi
    -0.39
     مشين
    -0.38
    anganese
    -0.37
    脱
    -0.37
     regn
    -0.37
    POSITIVE LOGITS
     disambiguazione
    0.47
    MessageOf
    0.44
    istoitu
    0.44
    rungsseite
    0.43
    rensa
    0.42
    ceğine
    0.42
    ătoare
    0.41
    rawDesc
    0.39
    endcsname
    0.39
    UrlResolution
    0.38
    Activations Density 0.094%

    No Known Activations