© 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. 24-GEMMASCOPE-RES-16K
    6. 716
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting elements used in coding or technical writing

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

    Text formatting: bolding or brackets

    np_acts-logits-general · gemini-2.0-flash

    legal and medical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ፩
    -0.55
     intptr
    -0.50
     '\\;'
    -0.46
    writeFieldEnd
    -0.46
     dataSnapshot
    -0.45
    rrggbb
    -0.44
    arrings
    -0.43
    consulté
    -0.43
    دانشنامهٔ
    -0.43
     actionTypes
    -0.42
    POSITIVE LOGITS
    :✨
    0.81
    adaptiveStyles
    0.40
    الدراسه
    0.40
    Портали
    0.38
    PAIGN
    0.36
     Numerade
    0.36
     Penge
    0.35
    																												
    0.35
    Summer
    0.35
    Бахар
    0.35
    Activations Density 0.164%

    No Known Activations