Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3185
    Prev
    Next
    INDEX
    Explanations

    website URLs and domain names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -1.06
    awtextra
    -1.04
     tartalomajánló
    -0.94
    ⓧ
    -0.90
    InputTagHelper
    -0.89
     ddelweddau
    -0.88
     &___
    -0.84
    帖最后由
    -0.82
    expandindo
    -0.81
    ]")]
    -0.81
    POSITIVE LOGITS
     O
    0.46
    /
    0.46
    O
    0.46
    po
    0.45
    tahui
    0.43
    …
    0.42
    ณ์
    0.42
     niñas
    0.41
    itarias
    0.40
    IS
    0.39
    Activations Density 0.360%

    No Known Activations