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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1100
    Prev
    Next
    INDEX
    Explanations

    terms related to the processes of consideration and evaluation in decision-making contexts

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

    "When" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    deciding or determining circumstances

    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
    تقاوى
    -0.63
    Personendaten
    -0.62
     TextAppearance
    -0.60
     onAnimation
    -0.58
     esquecer
    -0.57
    BeginContext
    -0.56
    ReactDOM
    -0.55
    AnchorStyles
    -0.55
    mlx
    -0.53
    <?
    -0.52
    POSITIVE LOGITS
     designing
    1.37
     planning
    1.33
     deciding
    1.26
     design
    1.15
    Designing
    1.13
     Designing
    1.09
     formulating
    1.07
     choosing
    1.07
     determining
    1.05
    planning
    1.04
    Activations Density 0.756%

    No Known Activations