© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 8805
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "announce" and related terms, indicating statements or declarations

    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
    didSet
    -0.56
    gebracht
    -0.46
     knock
    -0.44
    <tfoot>
    -0.44
    Historia
    -0.44
     knocked
    -0.43
    lotten
    -0.43
     <<<<<<<<<<<<<<
    -0.42
    drawiam
    -0.42
     nargin
    -0.42
    POSITIVE LOGITS
     intention
    0.83
    Portail
    0.82
     intentions
    0.80
     intent
    0.78
     themselves
    0.78
    //
    0.75
    Personensuche
    0.74
     Intent
    0.73
    脚注の使い方
    0.72
     légales
    0.72
    Activations Density 0.128%

    No Known Activations