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. 11594
    Prev
    Next
    INDEX
    Explanations

    information regarding official statements and responses from representatives and spokespeople

    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
     Perſ
    -0.52
    postmedia
    -0.51
    IBOutlet
    -0.51
     housewives
    -0.50
    BrowserModule
    -0.50
    ]=>
    -0.50
    PerformLayout
    -0.50
    áklad
    -0.48
     Wirklichkeit
    -0.48
    arschijnlijk
    -0.48
    POSITIVE LOGITS
    würfe
    0.56
    mişti
    0.54
    rítica
    0.53
    consulté
    0.53
    Carriera
    0.51
    landia
    0.51
     disputed
    0.50
    editorial
    0.50
    Портал
    0.50
     denied
    0.49
    Activations Density 0.153%

    No Known Activations