© 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. 14583
    Prev
    Next
    INDEX
    Explanations

    code that involves defining or interacting with data structures

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

    "tft" followed by other words

    np_acts-logits-general · gemini-2.0-flash

    tft.add_texture or ngx

    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
    hyrchwyd
    -0.53
    AsUp
    -0.51
    IndentedString
    -0.49
    ️⃣
    -0.48
     useRouter
    -0.46
     jäm
    -0.45
    FieldError
    -0.45
     צריך
    -0.45
    ADELPHIA
    -0.44
     publiek
    -0.44
    POSITIVE LOGITS
     Exactos
    0.78
    iprot
    0.72
     FetchType
    0.67
     >=",
    0.65
    principalColumn
    0.59
     kasarigan
    0.59
    TagMode
    0.58
    VolleyError
    0.57
    (&:
    0.57
    WebMethod
    0.55
    Activations Density 0.311%

    No Known Activations