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. 28-GEMMASCOPE-RES-16K
    6. 8092
    Prev
    Next
    INDEX
    Explanations

    terms and names relevant to biological taxonomy and classification

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

    ending in specific suffixes

    np_acts-logits-general · gemini-2.0-flash

    Latin suffixes ending words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crom
    -0.39
     برانيه
    -0.36
     cæ
    -0.35
     lccn
    -0.34
     genug
    -0.33
     дво
    -0.33
    Simply
    -0.32
     labd
    -0.32
     Hinter
    -0.31
    All
    -0.31
    POSITIVE LOGITS
    anyahu
    0.71
    featureID
    0.69
    balleur
    0.69
    aarrggbb
    0.67
    ロウィン
    0.64
     ModelRenderer
    0.63
     ErrIntOverflow
    0.62
     للاسماء
    0.59
     ModelExpression
    0.59
     betweenstory
    0.59
    Activations Density 0.202%

    No Known Activations