Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11302
    Prev
    Next
    INDEX
    Explanations

    contact information formats and related symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новништво
    -0.52
    InputBorder
    -0.44
    TargetException
    -0.43
    trường
    -0.41
    providedIn
    -0.40
    glPushMatrix
    -0.40
     låter
    -0.40
     téléphonique
    -0.39
     lyder
    -0.39
    ControllerAdvice
    -0.38
    POSITIVE LOGITS
     fax
    1.38
     Fax
    1.30
    Fax
    1.27
    fax
    1.19
     FAX
    1.13
    FAX
    1.11
     facsimile
    0.85
     email
    0.68
    Telefax
    0.66
     website
    0.64
    Activations Density 0.149%

    No Known Activations