© 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. 25-GEMMASCOPE-RES-16K
    6. 2926
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or ambiguity

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

    references to the word "something," indicating a focus on unspecified or vague subjects or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoScaleMode
    -0.68
    IntoConstraints
    -0.64
    Datuak
    -0.62
    مقاله
    -0.57
     ivelany
    -0.57
     segala
    -0.53
    mtrl
    -0.52
    ことは
    -0.51
    setVerticalGroup
    -0.49
     كومونز
    -0.49
    POSITIVE LOGITS
     else
    1.39
    Else
    0.92
    else
    0.86
     special
    0.81
     akin
    0.81
     Else
    0.80
     ELSE
    0.79
    ELSE
    0.74
    igshid
    0.72
    special
    0.65
    Activations Density 0.105%

    No Known Activations