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. 21-GEMMASCOPE-RES-16K
    6. 8585
    Prev
    Next
    INDEX
    Explanations

    concepts related to self-reflection and personal growth

    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
     Waray
    -0.60
    +#+
    -0.58
    EDEFAULT
    -0.55
    elemField
    -0.55
    ########.
    -0.54
     Vikipedi
    -0.54
    ướt
    -0.51
    ConstraintMaker
    -0.51
    jectory
    -0.50
    ActionMode
    -0.49
    POSITIVE LOGITS
     inside
    3.63
    inside
    3.19
     Inside
    3.18
    Inside
    3.16
     INSIDE
    2.88
     interior
    2.57
     internal
    2.56
    INSIDE
    2.55
     внутри
    2.46
     insides
    2.37
    Activations Density 0.685%

    No Known Activations