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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 81998
    Prev
    Next
    INDEX
    Explanations

    references to physical features and attributes of characters

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

    animal body parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ↺
    -0.50
    €)
    -0.48
     '\\;'
    -0.47
    CompleteListener
    -0.45
    IUrlHelper
    -0.45
    investment
    -0.44
    styleType
    -0.44
     يتيمه
    -0.44
     BytesLike
    -0.44
    bolista
    -0.43
    POSITIVE LOGITS
     fangs
    0.62
     feathers
    0.58
     antlers
    0.56
     horns
    0.56
     claws
    0.53
     beak
    0.50
     sayap
    0.45
     tooth
    0.45
     teeth
    0.45
     spike
    0.44
    Activations Density 0.052%

    No Known Activations