© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 13338
    Prev
    Next
    INDEX
    Explanations

    references to details or specifics in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WireFormatLite
    -0.57
    IntoConstraints
    -0.56
     pngtree
    -0.53
    ſelf
    -0.51
     jadx
    -0.51
     fprintf
    -0.51
     ſtill
    -0.50
    PROTOBUF
    -0.50
    Hentet
    -0.50
    MemoryWarning
    -0.49
    POSITIVE LOGITS
    Detail
    1.61
    detail
    1.40
    DETAIL
    1.20
     Detail
    1.05
    Details
    1.00
    DetailActivity
    0.81
     DETAIL
    0.80
    DetailView
    0.78
    Detalle
    0.73
    details
    0.72
    Activations Density 0.103%

    No Known Activations