© 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. 3274
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "with" in various contexts

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

    "With" followed by other tokens

    np_acts-logits-general · gemini-2.0-flash

    with respect to

    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
     the
    -0.69
    '},
    
    -0.69
     @"/
    -0.66
    )="
    -0.66
    YLE
    -0.65
    )}
    
    -0.63
     AssemblyVersion
    -0.63
     an
    -0.62
    '])){
    
    -0.61
    "])
    
    -0.60
    POSITIVE LOGITS
    with
    0.57
     destaque
    0.54
     with
    0.52
     withal
    0.50
     without
    0.49
     WITHOUT
    0.48
    without
    0.48
     zonder
    0.47
     WITH
    0.47
     associées
    0.47
    Activations Density 0.141%

    No Known Activations