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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 1073
    Prev
    Next
    INDEX
    Explanations

    expressions of personal pride and self-identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conmigo
    -0.60
    sidemargin
    -0.58
    Aktualisiert
    -0.56
     صوتيه
    -0.56
     Superintendent
    -0.56
     []:
    -0.54
    QUID
    -0.54
     Inscrivez
    -0.53
    tedrale
    -0.53
     comigo
    -0.51
    POSITIVE LOGITS
    зулта
    0.59
    AntiForgeryToken
    0.54
    webElementXpaths
    0.53
    ThroughAttribute
    0.50
    syms
    0.46
    PEAT
    0.42
    つもり
    0.41
    }}=$
    0.41
    flikt
    0.41
     linkovi
    0.41
    Activations Density 0.274%

    No Known Activations