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. 18-GEMMASCOPE-RES-16K
    6. 14390
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal assessments and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    applied to, dictated for, should be, staring at, happened to, dedicated to, directed at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brück
    -0.49
    sock
    -0.48
     Dernière
    -0.45
     ана
    -0.45
     bord
    -0.45
    uL
    -0.42
     KAL
    -0.42
    SSO
    -0.42
    posedge
    -0.41
    ocation
    -0.41
    POSITIVE LOGITS
     conmigo
    0.91
     kepad
    0.86
    MessageOf
    0.78
     חיצוניים
    0.76
    ViewImports
    0.74
     comigo
    0.73
     contigo
    0.72
    对自己
    0.72
    DrawerToggle
    0.71
    AutoresizingMask
    0.71
    Activations Density 0.391%

    No Known Activations