© 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. 2-GEMMASCOPE-RES-16K
    6. 5976
    Prev
    Next
    INDEX
    Explanations

    instances of the word "with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.76
    gridx
    -0.62
    !("{}",
    -0.58
     homes
    -0.57
    SizeF
    -0.57
    ])->
    -0.57
    principalColumn
    -0.56
     MotionEvent
    -0.55
    تماد
    -0.54
    ]--;
    -0.54
    POSITIVE LOGITS
    with
    1.21
    WITH
    1.10
    With
    0.68
     WITH
    0.68
    กับ
    0.63
    without
    0.62
    WithName
    0.61
    entyfik
    0.61
    dengan
    0.61
    avec
    0.61
    Activations Density 0.148%

    No Known Activations