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. 24-GEMMASCOPE-RES-16K
    6. 1068
    Prev
    Next
    INDEX
    Explanations

    key terms related to models, frameworks, and structural systems in economic and organizational contexts

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

    models, styles, methods, or principles

    np_acts-logits-general · gemini-2.0-flash

    method, style, principle, model

    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
    almaz
    -0.43
    TableAdapter
    -0.39
    CppMethod
    -0.39
    籬
    -0.39
    RTLI
    -0.39
    UserScript
    -0.38
     SPEECH
    -0.38
     utafitiHapana
    -0.38
     "..\..\
    -0.38
    COLLE
    -0.38
    POSITIVE LOGITS
    方式
    0.70
     método
    0.65
     approach
    0.65
     méthode
    0.62
     method
    0.60
     estilo
    0.58
    approach
    0.56
     metodología
    0.55
    แบบ
    0.54
     style
    0.53
    Activations Density 1.297%

    No Known Activations