© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8447
    Prev
    Next
    INDEX
    Explanations

    concepts related to secrecy and the implications of keeping information hidden

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

    secrets or concealment

    np_acts-logits-general · gemini-2.0-flash

    secretive or hidden states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.61
     initComponents
    -0.59
     gynhyrchwyd
    -0.57
    MigrationBuilder
    -0.55
    antMatchers
    -0.55
    ValueStyle
    -0.54
     AssemblyCulture
    -0.53
    ArgsConstructor
    -0.53
    addComponent
    -0.52
    AnchorTagHelper
    -0.51
    POSITIVE LOGITS
     secret
    2.36
     hidden
    2.18
     secrecy
    2.18
     secretive
    2.02
    secret
    2.01
     concealed
    1.94
     secretly
    1.91
     Secret
    1.88
    hidden
    1.87
     hiding
    1.86
    Activations Density 0.685%

    No Known Activations