© 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. 851
    Prev
    Next
    INDEX
    Explanations

    references to parameters and attributes in a structured data format

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

    Reference to figures or IDs

    np_acts-logits-general · gemini-2.0-flash

    figures and identifiers

    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
     ModelExpression
    -0.92
    principalTable
    -0.86
     Италијани
    -0.86
    WriteBarrier
    -0.83
     Савезне
    -0.81
    fjspx
    -0.81
    DeleteBehavior
    -0.80
    تقاوى
    -0.79
     betweenstory
    -0.79
    libft
    -0.78
    POSITIVE LOGITS
    )
    0.60
    "
    0.59
    ()
    0.58
    er
    0.55
    }
    0.54
    ه
    0.52
    ي
    0.51
    ”
    0.49
    multicolumn
    0.49
    {}
    0.49
    Activations Density 0.436%

    No Known Activations