© 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. 16-GEMMASCOPE-RES-16K
    11. 4801
    Prev
    Next
    INDEX
    Explanations

    statements of causation or correlation regarding observations or results

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

    Follows verbs like "suggest", "indicate", "realize", or "know"

    np_acts-logits-general · gemini-2.0-flash

    stating findings and conclusions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setAddress
    -0.51
    Jedis
    -0.49
    difice
    -0.49
     ddelweddau
    -0.48
    ของคุณ
    -0.47
    NewLabel
    -0.46
    uskas
    -0.46
    SOUNDBITE
    -0.46
     */;
    -0.45
     Gea
    -0.45
    POSITIVE LOGITS
     there
    1.21
     that
    1.15
     they
    1.15
     we
    0.82
    there
    0.75
     it
    0.74
    AutoScaleMode
    0.64
     EconPapers
    0.64
     nobody
    0.63
     theres
    0.63
    Activations Density 0.654%

    No Known Activations