© 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. 2720
    Prev
    Next
    INDEX
    Explanations

    structured dialogues and conversational exchanges

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

    punctuation marks and structural separators (periods, parentheses, commas used to denote breaks or transitions).

    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
    UrlResolution
    -0.59
    IsContent
    -0.51
    RenderAtEndOf
    -0.47
     Lightboxes
    -0.46
     protoimpl
    -0.45
    Beneficios
    -0.45
    LookAnd
    -0.45
    etCode
    -0.45
     FetchType
    -0.44
    othelioma
    -0.43
    POSITIVE LOGITS
     fans
    0.64
    Interestingly
    0.61
    Fans
    0.60
     unsur
    0.59
     Interestingly
    0.58
     Apparently
    0.56
    Elsewhere
    0.56
    Needless
    0.56
     Looks
    0.55
     Meanwhile
    0.55
    Activations Density 0.224%

    No Known Activations