© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4739
    Prev
    Next
    INDEX
    Explanations

    phrases relating to spatial relationships and placement within contexts

    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
    ↵
    -0.52
    TagMode
    -0.49
    })();
    -0.46
    aterally
    -0.46
    ++];
    -0.40
    --
    -0.40
    *=
    -0.40
    <eos>
    -0.40
    eterminate
    -0.39
    mandi
    -0.39
    POSITIVE LOGITS
     pouvoit
    0.86
     auroit
    0.86
     feroit
    0.84
    TargetException
    0.77
     contigo
    0.68
     Administrativna
    0.68
     détru
    0.68
     avoient
    0.67
     ainfi
    0.66
     étoit
    0.66
    Activations Density 0.295%

    No Known Activations