© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6701
    Prev
    Next
    INDEX
    Explanations

    the word "for" in various contexts, indicating a focus on purpose or reasoning

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

    "For" followed by a personal pronoun

    np_acts-logits-general · gemini-2.0-flash

    "for" followed by personal or general references

    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
    MLLoader
    -0.87
    +#+
    -0.79
     TestBed
    -0.71
    errHandler
    -0.67
    writeFieldEnd
    -0.67
    localctx
    -0.67
    IsContent
    -0.64
     TextAppearance
    -0.64
     ModelExpression
    -0.64
    testify
    -0.63
    POSITIVE LOGITS
     me
    1.33
     us
    1.10
     them
    0.84
     him
    0.83
     everyone
    0.76
     someone
    0.76
     anyone
    0.76
     everybody
    0.68
     anybody
    0.64
     both
    0.62
    Activations Density 0.204%

    No Known Activations