© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8125
    Prev
    Next
    INDEX
    Explanations

    configuration files and their associated operations or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.88
     HasFactory
    -0.81
    ThroughAttribute
    -0.70
    Personensuche
    -0.69
    principalColumn
    -0.68
     незавершена
    -0.68
     ElementRef
    -0.68
     useHistory
    -0.68
    >//
    -0.67
    Composable
    -0.67
    POSITIVE LOGITS
     détaillés
    0.58
     getopt
    0.53
    FormTagHelper
    0.51
     trade
    0.47
     potuto
    0.46
    參
    0.46
     Scroll
    0.45
    ruce
    0.45
    TextColor
    0.45
     Pradesh
    0.43
    Activations Density 0.298%

    No Known Activations