Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8068
    Prev
    Next
    INDEX
    Explanations

    specific terms related to measurement and evaluation, particularly within scientific or analytical contexts

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

    followed by prepositions or articles

    np_acts-logits-general · gemini-2.0-flash

    common introductory phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.85
    ).
    -0.77
    ++.
    -0.76
    }$.
    -0.74
    ."""
    -0.74
    。
    -0.74
    }}$.
    -0.74
    .
    
    -0.73
    ;
    -0.71
    ".
    -0.70
    POSITIVE LOGITS
     beginnetje
    0.96
    SourceChecksum
    0.83
     AssemblyCulture
    0.83
     الحره
    0.78
     δὲ
    0.77
     AssemblyCompany
    0.76
    AndEndTag
    0.75
    XmlAccessorType
    0.75
     these
    0.75
    sidemargin
    0.74
    Activations Density 0.964%

    No Known Activations