Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 150
    Prev
    Next
    INDEX
    Explanations

    narrative elements that describe tension or conflict in a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.74
    tvguidetime
    -0.65
    AndEndTag
    -0.61
    Vidite
    -0.58
    webElementXpaths
    -0.56
    enterOuterAlt
    -0.56
    zyl
    -0.53
    createCanvas
    -0.53
    ochet
    -0.53
    #+#
    -0.52
    POSITIVE LOGITS
     silence
    1.53
    silence
    1.34
    Silence
    1.27
     Silence
    1.26
     silent
    1.11
     silencio
    1.04
     silêncio
    0.98
    沉默
    0.97
    silent
    0.92
     silently
    0.91
    Activations Density 0.112%

    No Known Activations