© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3021
    Prev
    Next
    INDEX
    Explanations

    concepts related to heat treatment and processing methods

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

    preceding adverbs/qualifiers

    np_acts-logits-general · gemini-2.0-flash

    consequences and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.69
     
    -0.60
     die
    -0.48
     til
    -0.47
     il
    -0.47
     porque
    -0.45
    哭了
    -0.45
     died
    -0.45
    に戻
    -0.44
    </table>
    -0.44
    POSITIVE LOGITS
     justement
    1.16
     durchaus
    1.11
     indeed
    1.09
     nemlig
    1.08
     ciertamente
    1.05
     весьма
    1.04
    apimachinery
    1.02
     whatsoever
    1.01
    RenderAtEndOf
    1.00
     justamente
    0.99
    Activations Density 4.027%

    No Known Activations