© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8203
    Prev
    Next
    INDEX
    Explanations

    discussions or narrations related to personal anecdotes or storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding a clause

    np_acts-logits-general · gemini-2.0-flash

    how something is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerNonUser
    -0.43
    aktur
    -0.38
    IContainer
    -0.38
    WireFormatLite
    -0.37
    jspb
    -0.37
    IntoConstraints
    -0.37
    providedIn
    -0.34
    SpringBootTest
    -0.34
    PointerException
    -0.34
     FormData
    -0.34
    POSITIVE LOGITS
     how
    2.19
     cómo
    1.54
    how
    1.48
     bagaimana
    1.38
    How
    1.27
     How
    1.21
     كيف
    1.20
     چگونه
    1.20
     hvordan
    1.20
    如何
    1.18
    Activations Density 0.311%

    No Known Activations