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. 8288
    Prev
    Next
    INDEX
    Explanations

    themes related to uncovering hidden truths and exploring deep emotional aspects of human nature

    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
    MigrationBuilder
    -0.72
    évaluateur
    -0.61
    queryInterface
    -0.53
    fjspx
    -0.50
     bezeichneter
    -0.50
    QMetaType
    -0.49
    ngOnInit
    -0.49
     Vorder
    -0.48
     entradas
    -0.48
    addPreferredGap
    -0.47
    POSITIVE LOGITS
     hidden
    1.90
     lurking
    1.58
     hiding
    1.57
    hidden
    1.57
     buried
    1.48
     concealed
    1.46
    Hidden
    1.44
     Hidden
    1.43
     Hiding
    1.34
     lur
    1.31
    Activations Density 0.420%

    No Known Activations