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. 4336
    Prev
    Next
    INDEX
    Explanations

    instances of the word "However" and its variations, indicating a transition or contrast in ideas

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

    Follows the word "However"

    np_acts-logits-general · gemini-2.0-flash

    However, introducing contrast

    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
     aber
    -0.63
     createSlice
    -0.62
     estekak
    -0.59
     pero
    -0.59
    DebuggerNonUser
    -0.57
    可是
    -0.56
    fromCharCode
    -0.56
    rrggbb
    -0.55
    mapStateToProps
    -0.55
    mtrl
    -0.55
    POSITIVE LOGITS
     demikian
    0.78
     interestingly
    0.71
     unlike
    0.71
     unfortunate
    0.67
     difficult
    0.67
     unintentional
    0.65
     slight
    0.63
     strangely
    0.63
     oddly
    0.63
     much
    0.62
    Activations Density 0.126%

    No Known Activations