© 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. 6491
    Prev
    Next
    INDEX
    Explanations

    conditional statements in programming code

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

    Following "if" and checking conditions

    np_acts-logits-general · gemini-2.0-flash

    negated conditional statements

    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
     GenerationType
    -0.79
    Hochspringen
    -0.74
    fjspx
    -0.61
     برانيه
    -0.61
    Portale
    -0.60
    Einzelnachweise
    -0.58
    iNdEx
    -0.57
    askar
    -0.57
    cshtml
    -0.57
    Manbalar
    -0.56
    POSITIVE LOGITS
     !$
    0.84
     !
    0.74
    assertFalse
    0.73
    (!
    0.73
    (!$
    0.69
     (!
    0.64
    {!
    0.63
    :!
    0.63
     نکرد
    0.61
     !_
    0.60
    Activations Density 0.078%

    No Known Activations