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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2327
    Prev
    Next
    INDEX
    Explanations

    contexts and configurations related to API requests and subscriptions

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

    Code constructs specifying context

    np_acts-logits-general · gemini-2.0-flash

    context and handlers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.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
    marle
    -0.58
     Charge
    -0.50
     felizes
    -0.46
    nible
    -0.46
     charge
    -0.45
    LookAnd
    -0.45
     CHARGE
    -0.44
    Charge
    -0.44
    bilisi
    -0.43
     kine
    -0.43
    POSITIVE LOGITS
     context
    3.61
    context
    3.44
     Context
    2.81
    Context
    2.70
     contexto
    2.49
     CONTEXT
    2.45
     contexts
    2.41
    CONTEXT
    2.37
     contex
    2.22
     contexte
    2.21
    Activations Density 0.127%

    No Known Activations