© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15980
    Prev
    Next
    INDEX
    Explanations

    expressions of agreement or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :",
    -0.76
    _"+
    -0.74
    딘
    -0.74
     CEN
    -0.71
     Roc
    -0.71
    るのが
    -0.70
    emi
    -0.70
     PEN
    -0.69
    forChild
    -0.68
    )):
    -0.67
    POSITIVE LOGITS
     aswell
    1.01
     nahilalakip
    0.90
    mybatisplus
    0.80
     CreateTagHelper
    0.79
     TAMBÉM
    0.78
    enderror
    0.74
    väl
    0.74
     cũng
    0.71
    Cześć
    0.71
     مرئيه
    0.71
    Activations Density 0.055%

    No Known Activations