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. 21-GEMMASCOPE-RES-16K
    6. 1194
    Prev
    Next
    INDEX
    Explanations

    terms related to cellular culture conditions and the parameters used in experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerNonUser
    -0.60
    LookAnd
    -0.58
     CURIAM
    -0.57
     <<<<<<<<<<<<<<
    -0.57
    DockStyle
    -0.56
    StoryboardSegue
    -0.55
     Vikipedi
    -0.52
     Ly
    -0.48
    AndPassword
    -0.47
    Péri
    -0.47
    POSITIVE LOGITS
     CO
    1.68
     carbon
    1.51
    CO
    1.46
     Carbon
    1.35
    Carbon
    1.29
    carbon
    1.27
     CARBON
    1.25
     gas
    1.08
    CARBON
    1.06
     dioxide
    1.03
    Activations Density 0.438%

    No Known Activations