© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14658
    Prev
    Next
    INDEX
    Explanations

    mentions of guarantees or assurances

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1527
    +0.14
    0.5%
    596
    +0.14
    0.5%
    1896
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1527
    +0.14
    0.03
    596
    +0.14
    0.02
    1983
    +0.13
    0.02
    Negative Logits
     Kategor
    -0.69
     Strukt
    -0.61
     konserv
    -0.60
     kosme
    -0.58
     praktik
    -0.58
     vost
    -0.57
     akut
    -0.57
     konsult
    -0.57
     antik
    -0.56
     taba
    -0.56
    POSITIVE LOGITS
     guarantee
    1.12
     guaranteed
    1.06
     guarantees
    1.04
     Guaranteed
    0.98
     Guarantee
    0.96
    anteed
    0.96
     guaranteeing
    0.91
     Guarante
    0.86
    Guaranteed
    0.84
    guar
    0.83
    Activations Density 0.075%

    No Known Activations