© 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. 3562
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate contrast or alternatives

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

    the phrase "Instead of" used to introduce contrasts or alternatives.

    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
    :✨
    -0.55
     Wikimedijinoj
    -0.49
    lgari
    -0.47
    ❋
    -0.46
     resourceCulture
    -0.45
     houſe
    -0.45
     himo
    -0.44
    ➟
    -0.43
     ſeveral
    -0.43
    UrlResolution
    -0.43
    POSITIVE LOGITS
     than
    0.62
     niż
    0.45
    })`
    0.43
     opting
    0.41
    于
    0.40
    sm
    0.40
     betweenstory
    0.39
     milliers
    0.39
     disambiguazione
    0.39
    than
    0.38
    Activations Density 0.064%

    No Known Activations