© 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. 4752
    Prev
    Next
    INDEX
    Explanations

    elements related to personal identity and narrative

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

    Beginning of diary, memoir, or journal entries

    np_acts-logits-general · gemini-2.0-flash

    memoir autobiographical journal forms

    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
     برانيه
    -0.66
    posedge
    -0.59
    NullCheck
    -0.58
     agrí
    -0.53
     compositeur
    -0.50
     hectáreas
    -0.49
    Encyklopedia
    -0.49
    compute
    -0.48
    endpush
    -0.48
    npm
    -0.48
    POSITIVE LOGITS
     diary
    0.92
     memoir
    0.88
     autobiography
    0.86
     autobio
    0.82
    diary
    0.76
     observations
    0.76
     vig
    0.76
     stream
    0.74
     journal
    0.74
     anecdotal
    0.69
    Activations Density 0.228%

    No Known Activations