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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 6226
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of software development processes and techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BufferException
    -0.74
     defStyle
    -0.63
    发表于
    -0.62
    IContainer
    -0.60
    LookAnd
    -0.60
     Meksiku
    -0.57
    FunctionFlags
    -0.56
    TintMode
    -0.56
     defaultstate
    -0.56
    jsii
    -0.55
    POSITIVE LOGITS
     виправивши
    0.70
    setVerticalGroup
    0.66
    setContentView
    0.58
    stornos
    0.50
     ModelExpression
    0.49
     instance
    0.49
     CreateTagHelper
    0.49
    abestanden
    0.48
     Chwiliwch
    0.48
    MMV
    0.48
    Activations Density 2.679%

    No Known Activations