© 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. 28-GEMMASCOPE-RES-16K
    6. 7784
    Prev
    Next
    INDEX
    Explanations

    user directory paths and file information

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

    File paths or directory structures

    np_acts-logits-general · gemini-2.0-flash

    user directory paths

    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
     '\\;'
    -0.40
     föruts
    -0.38
     dist
    -0.38
     Tengah
    -0.36
     gekomen
    -0.35
    WritableDatabase
    -0.35
    webElementXpaths
    -0.34
     carefully
    -0.34
     rowspan
    -0.34
     älskar
    -0.34
    POSITIVE LOGITS
     kasarigan
    0.65
     يتيمه
    0.61
     мәкал
    0.58
     EconPapers
    0.57
     ***!
    0.56
     Numerade
    0.56
    administrator
    0.55
     Administrativna
    0.54
     Administrator
    0.53
     дописавши
    0.53
    Activations Density 0.044%

    No Known Activations