© 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. 31-GEMMASCOPE-RES-16K
    6. 615
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "RO" and its variations

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

    two-letter sequences that are parts of proper nouns or abbreviated terms.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nat
    -0.25
    uss
    -0.25
     chạy
    -0.25
     burbujas
    -0.24
     medesimo
    -0.24
     Greif
    -0.24
     aguda
    -0.24
     Aufenthalts
    -0.24
     CLAIMS
    -0.24
     Tenggara
    -0.23
    POSITIVE LOGITS
    ChildScrollView
    0.73
     purpoſe
    0.70
    pportun
    0.65
     BoxFit
    0.65
    SuppressLint
    0.65
     houſe
    0.63
    PositiveButton
    0.63
     AdapterView
    0.61
     ſte
    0.60
     ſol
    0.59
    Activations Density 0.399%

    No Known Activations