Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 870
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuations typically used in programming code or data formats

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

    numeric digits and decimal numbers in mathematical expressions and code.

    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
    ReusableCell
    -0.77
    Билгалдахарш
    -0.69
    Hentet
    -0.69
    StoryboardSegue
    -0.65
    GetAxis
    -0.62
    httphttps
    -0.61
    دانشنامهٔ
    -0.60
    rungsseite
    -0.60
    Autoritní
    -0.59
    ChildScrollView
    -0.57
    POSITIVE LOGITS
     its
    0.38
    IENT
    0.38
     Its
    0.37
    enial
    0.35
    tabular
    0.35
    Its
    0.34
     Otter
    0.33
     bes
    0.33
       
    0.31
    })();
    
    0.30
    Activations Density 0.373%

    No Known Activations