© 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. 14066
    Prev
    Next
    INDEX
    Explanations

    contextual cues related to financial transactions or investment decisions

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

    Text between quotation marks

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation followed by text

    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
     according
    -0.73
     reportedly
    -0.69
     respective
    -0.67
     accordingly
    -0.64
    зулта
    -0.63
    According
    -0.61
    tvguidetime
    -0.61
     अनुसार
    -0.60
     regarding
    -0.60
     CreateTagHelper
    -0.60
    POSITIVE LOGITS
     ``
    0.61
    yelitis
    0.56
     ''
    0.54
     spokeswoman
    0.52
    vallis
    0.51
     "
    0.50
     zato
    0.50
    ``
    0.48
     ‘‘
    0.48
    ränkt
    0.48
    Activations Density 0.120%

    No Known Activations