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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14477
    Prev
    Next
    INDEX
    Explanations

    references to film production and its budgeting aspects

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

    followed by prepositions or parentheses

    np_acts-logits-general · gemini-2.0-flash

    standards of comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.42
    exact
    -0.39
     PROTE
    -0.38
    ույ
    -0.36
     δο
    -0.36
     PLAINT
    -0.35
    onatos
    -0.35
     construido
    -0.35
     Spaß
    -0.35
     perang
    -0.35
    POSITIVE LOGITS
     kasarigan
    0.65
    ंदीखरीदारी
    0.52
     Infórmanos
    0.52
     kaynağından
    0.50
    relativeTime
    0.47
     Compared
    0.45
     <<<<<<<<<<<<<<
    0.43
     Numerade
    0.43
    Compared
    0.43
    TagHelper
    0.43
    Activations Density 0.298%

    No Known Activations