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. 25-GEMMASCOPE-RES-16K
    6. 15759
    Prev
    Next
    INDEX
    Explanations

    relationships and distinctions among types of collaboration and evidence in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.55
    ValueStyle
    -0.50
     surla
    -0.47
     snippetHide
    -0.47
    windowFixed
    -0.44
     apellidos
    -0.41
    JspWriter
    -0.41
    setVerticalGroup
    -0.40
    AutoScaleMode
    -0.40
    tinyos
    -0.40
    POSITIVE LOGITS
     types
    1.22
     type
    0.97
     kinds
    0.91
     Types
    0.90
     tipos
    0.86
    types
    0.86
     jenis
    0.82
     TYPES
    0.81
     tipo
    0.80
    类型
    0.78
    Activations Density 0.737%

    No Known Activations