© 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. 16-GEMMASCOPE-RES-16K
    11. 1320
    Prev
    Next
    INDEX
    Explanations

    information regarding the outcome or result of various situations

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

    non-English language text

    np_acts-logits-general · gemini-2.0-flash

    verbs of possibility and occurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     you
    -0.53
     we
    -0.53
     yourself
    -0.48
     people
    -0.43
     himself
    -0.43
    we
    -0.42
     ourselves
    -0.41
     them
    -0.40
     using
    -0.39
     myself
    -0.38
    POSITIVE LOGITS
     AssemblyCulture
    1.10
    ConstraintMaker
    0.97
     NSCoder
    0.92
    WriteTagHelper
    0.87
    ſelves
    0.84
     itſelf
    0.83
    ]")]
    0.81
    elemField
    0.78
    IndentedString
    0.78
     onPostExecute
    0.78
    Activations Density 0.083%

    No Known Activations