© 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. 22-GEMMASCOPE-RES-16K
    11. 5676
    Prev
    Next
    INDEX
    Explanations

    the presence of unique or special characters and whitespace variations

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

    Hexadecimal code representations

    np_acts-logits-general · gemini-2.0-flash

    URL and code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -0.58
    <em>
    -0.49
    <i>
    -0.46
     ushort
    -0.42
    <sup>
    -0.41
    …
    -0.40
    .
    -0.40
    The
    -0.40
    <b>
    -0.40
    <eos>
    -0.40
    POSITIVE LOGITS
    AddTagHelper
    1.32
    DockStyle
    1.30
    AnchorStyles
    1.20
    mybatisplus
    1.19
     propOrder
    1.12
    UrlResolution
    1.10
     '\\;'
    1.09
     ModelExpression
    1.08
    IsMutable
    1.08
    MessageTagHelper
    1.07
    Activations Density 0.330%

    No Known Activations