© 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. 21-GEMMASCOPE-RES-16K
    11. 1154
    Prev
    Next
    INDEX
    Explanations

    strings of code with specific formatting or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oni
    -0.46
    <em>
    -0.41
     asegurarse
    -0.40
    ംബ
    -0.39
    "?
    -0.39
    ?
    -0.39
    larak
    -0.38
    </strong>
    -0.37
    ulu
    -0.37
    into
    -0.36
    POSITIVE LOGITS
    //
    1.03
    #+#
    1.00
     المعيارى
    0.96
     CreateTagHelper
    0.91
     EconPapers
    0.89
    +#+
    0.83
    onAttach
    0.82
    IsContent
    0.81
     ModelExpression
    0.79
    #
    0.79
    Activations Density 0.059%

    No Known Activations