© 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. 18-GEMMASCOPE-RES-16K
    11. 2972
    Prev
    Next
    INDEX
    Explanations

    numerical values and specific identifiers

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

    Lines of code with index and cur values

    np_acts-logits-general · gemini-2.0-flash

    {cur: ..., idx: ...}

    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
     kasarigan
    -0.79
    IntoConstraints
    -0.74
    
    -0.59
     Monfieur
    -0.59
     дописавши
    -0.59
    دد
    -0.56
     Ανακτήθηκε
    -0.54
    WithMany
    -0.54
    ॉग
    -0.54
     Pristup
    -0.54
    POSITIVE LOGITS
    djangoproject
    0.52
    xmlhttp
    0.49
    achella
    0.49
    anyahu
    0.48
    brough
    0.48
    olsom
    0.46
    };*/
    0.46
    onAttach
    0.46
    vician
    0.44
    TargetException
    0.44
    Activations Density 0.333%

    No Known Activations