© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 4893
    Prev
    Next
    INDEX
    Explanations

    actions related to development and exploration in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NgModule
    -0.56
    Personendaten
    -0.56
    ništvo
    -0.54
     '\\;'
    -0.54
    pushFollow
    -0.54
    manjaro
    -0.54
    verifyException
    -0.52
    maras
    -0.51
     agrees
    -0.51
     OnTriggerEnter
    -0.50
    POSITIVE LOGITS
     elaboration
    0.98
     vidare
    0.96
     further
    0.93
     videre
    0.86
    further
    0.83
     expand
    0.82
     Ausbau
    0.80
     elaborated
    0.79
    Further
    0.79
     Elabor
    0.78
    Activations Density 0.486%

    No Known Activations