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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1154
    Prev
    Next
    INDEX
    Explanations

    references to violent and destructive scenarios

    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
    856
    +0.14
    0.4%
    381
    +0.14
    0.4%
    604
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.14
    0.05
    940
    +0.14
    0.02
    1801
    +0.12
    0.01
    Negative Logits
     maksi
    -1.47
     antik
    -1.21
     makro
    -1.19
    Yess
    -1.15
     keramik
    -1.09
     lemp
    -1.09
     optik
    -1.09
     ekos
    -1.08
     territo
    -1.06
     jati
    -1.05
    POSITIVE LOGITS
     kinda
    0.77
     apparently
    0.72
     yeah
    0.71
     chanteur
    0.70
     probably
    0.70
     weird
    0.70
     pissed
    0.69
     basically
    0.69
     fucking
    0.68
     dude
    0.67
    Activations Density 0.348%

    No Known Activations