© 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. 14444
    Prev
    Next
    INDEX
    Explanations

    references to observations and experiences related to individuals and their actions

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

    followed by a quotation mark

    np_acts-logits-general · gemini-2.0-flash

    words followed by descriptions

    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
     sahiptir
    -0.76
    ########.
    -0.53
     purpoſe
    -0.53
    ugier
    -0.53
     göre
    -0.52
     mourut
    -0.52
     affinch
    -0.50
    abab
    -0.50
    MethodManager
    -0.49
     '{@
    -0.49
    POSITIVE LOGITS
     coming
    0.99
     emerge
    0.95
     unfold
    0.91
     come
    0.84
     popping
    0.84
     evolve
    0.83
     firsthand
    0.79
     disappear
    0.78
     being
    0.78
     peeking
    0.77
    Activations Density 0.255%

    No Known Activations