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. 18-GEMMASCOPE-RES-16K
    6. 1555
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation marks and sentence delimiters

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

    Sentences that begin with coordinating conjunctions

    np_acts-logits-general · gemini-2.0-flash

    end of sentence, lists, conjunctions

    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
    principalTable
    -1.27
    tagHelperRunner
    -1.04
    </caption>
    -0.97
    IsMutable
    -0.90
     الرياضيه
    -0.90
     nahilalakip
    -0.90
    IntoConstraints
    -0.90
    ".
    
    -0.86
    }>;
    -0.86
     GenerationType
    -0.86
    POSITIVE LOGITS
    <eos>
    0.99
    The
    0.75
     The
    0.64
    ----------------
    0.60
    Finally
    0.57
    ****************
    0.57
    Also
    0.57
    This
    0.56
    I
    0.54
     Finally
    0.54
    Activations Density 0.696%

    No Known Activations