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. 14-GEMMASCOPE-RES-16K
    6. 169
    Prev
    Next
    INDEX
    Explanations

    phrases and terminology related to justifiable homicides and the disparities in treatment of cases involving different racial backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EditorBrowsable
    -0.58
     AssemblyCulture
    -0.53
    simpleType
    -0.52
    |}{\
    -0.50
    jboss
    -0.50
    scriptcase
    -0.48
    ++];
    -0.48
    stateParams
    -0.48
    NUMX
    -0.48
    presso
    -0.47
    POSITIVE LOGITS
     sebanyak
    0.76
     nearly
    0.63
     Nearly
    0.60
    nearly
    0.58
     lenker
    0.57
    Nearly
    0.57
     Altogether
    0.55
     only
    0.55
     muitas
    0.55
    ONLY
    0.55
    Activations Density 0.720%

    No Known Activations